linkedin-post

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious behaviors, command execution, or data exfiltration attempts were detected. The skill primarily consists of markdown templates and natural language instructions for content creation.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process data from external Notion databases (notion_notion-search and notion_notion-fetch) which could theoretically contain malicious instructions. However, this is the intended functionality for cross-referencing performance data. Evidence: 1. Ingestion points: notion_notion-search and notion_notion-fetch in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Text generation/drafting. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 01:32 PM